Create, retrieve, update and delete Azure Custom Vision projects
create_classification_project(endpoint, name, domain = "general", export_target = c("none", "standard", "vaidk"), multiple_tags = FALSE, description = NULL) create_object_detection_project(endpoint, name, domain = "general", export_target = c("none", "standard", "vaidk"), description = NULL) list_projects(endpoint) get_project(endpoint, name = NULL, id = NULL) update_project(endpoint, name = NULL, id = NULL, domain = "general", export_target = c("none", "standard", "vaidk"), multiple_tags = FALSE, description = NULL) delete_project(object, ...)
endpoint: A custom vision endpoint.name, id: The name and ID of the project. At least one of these must be specified for get_project, update_project and delete_project. The name is required for create_project (the ID will be assigned automatically).domain: What kinds of images the model is meant to apply to. The default "general" means the model is suitable for use in a generic setting. Other, more specialised domains for classification include "food", "landmarks" and "retail"; for object detection the other possible domain is "logo".export_target: What formats are supported when exporting the model.multiple_tags: For classification models, Whether multiple categories (tags/labels) for an image are allowed. The default is FALSE, meaning an image represents one and only one category. Ignored for object detection models.description: An optional text description of the project.object: For delete_customvision_project, either an endpoint, or a project object....: Further arguments passed to lower-level methods.delete_project returns NULL invisibly, on a successful deletion. The others return an object of class customvision_project.
A Custom Vision project contains the metadata for a model: its intended purpose (classification vs object detection), the domain, the set of training images, and so on. Once you have created a project, you upload images to it, and train models based on those images. A trained model can then be published as a predictive service, or exported for standalone use.
By default, a Custom Vision project does not support exporting the model; this allows it to be more complex, and thus potentially more accurate. Setting export_target="standard" enables exporting to the following formats:
Setting export_target="vaidk" allows exporting to Vision AI Development Kit format, in addition to the above.
## Not run: endp <- customvision_training_endpoint(url="endpoint_url", key="key") create_classification_project(endp, "myproject") create_classification_project(endp, "mymultilabelproject", multiple_tags=TRUE) create_object_detection_project(endp, "myobjdetproj") create_classification_project(endp, "mystdproject", export_target="standard") list_projects(endp) get_project(endp, "myproject") update_project(endp, "myproject", export_target="vaidk") ## End(Not run)
customvision_training_endpoint, add_images, train_model, publish_model, predict.customvision_model, do_training_op